This PR will help in maintaining consistency of training results by saving the embeddings created.
In accordance with issue 62- https://github.com/zhiguowang/BiMPM/issues/62
This embedding can then be used as a SentenceMatchDecoder.py without any conflict.
This PR will help in maintaining consistency of training results by saving the embeddings created. In accordance with issue 62- https://github.com/zhiguowang/BiMPM/issues/62 This embedding can then be used as a SentenceMatchDecoder.py without any conflict.